INDEX

Explanations

phrases indicating actions and conditions related to processes and systems

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erva

-0.15

 Heard

-0.14

acob

-0.14

Stencil

-0.14

erv

-0.14

ect

-0.14

keh

-0.13

opot

-0.13

 Katz

-0.13

Ð°ÑĤÐ¾Ð²

-0.13

POSITIVE LOGITS

DEM

0.16

ypi

0.16

Instead

0.15

instead

0.15

 Rather

0.15

 Instead

0.15

coni

0.15

ikel

0.14

Rather

0.14

iken

0.14

Activations Density 0.032%

phrases indicating actions and conditions related to processes and systems

No Comments

No Known Activations